Skip to main content

MCP server for csv analytics. Features load csv, query data, describe columns. From MEOK AI Labs.

Project description

Csv Analytics MCP

MCP server for csv analytics mcp operations

PyPI License: MIT MEOK AI Labs

Overview

Csv Analytics MCP provides AI-powered tools via the Model Context Protocol (MCP).

Tools

Tool Description
load_csv Load a CSV file into memory for analysis. The dataset is stored under
query_data Query a loaded dataset with filtering, column selection, and sorting.
describe_columns Get detailed statistics for every column in a dataset:
aggregate Aggregate data with GROUP BY and compute metrics.
export_chart_data Export data in a chart-ready format. Output is compatible with Chart.js,
pivot_table Create a pivot table from a dataset. Reshapes data by grouping rows

Installation

pip install meok-csv-analytics-mcp

Usage with Claude Desktop

Add to your Claude Desktop MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "csv-analytics-mcp": {
      "command": "python",
      "args": ["-m", "meok_csv_analytics_mcp.server"]
    }
  }
}

Usage with FastMCP

from mcp.server.fastmcp import FastMCP

# This server exposes 6 tool(s) via MCP
# See server.py for full implementation

License

MIT © MEOK AI Labs


Pairs with MEOK Governance Suite

Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool — EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.

# One-shot install of the governance pack
npx meok-setup --pack governance

Free tier: 10 calls/day per MCP. Pro tier (£79/mo): unlimited + cryptographically signed compliance attestations your auditor verifies independently.

→ Full catalogue: councilof.ai/catalogue → MEOK AI Labs: meok.ai

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

csv_analytics_mcp-1.0.6.tar.gz (17.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

csv_analytics_mcp-1.0.6-py3-none-any.whl (9.3 kB view details)

Uploaded Python 3

File details

Details for the file csv_analytics_mcp-1.0.6.tar.gz.

File metadata

  • Download URL: csv_analytics_mcp-1.0.6.tar.gz
  • Upload date:
  • Size: 17.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for csv_analytics_mcp-1.0.6.tar.gz
Algorithm Hash digest
SHA256 87f8b27efd15b99cf39273f470e520a228bffa44d7a9d238592223678d151a0f
MD5 fc55c2ad76cd282089b9ad0fc2bb2711
BLAKE2b-256 75682e958a73d76b73cfd77823aed7f3e8d4b52d91fd86e5d272c40a5439d064

See more details on using hashes here.

File details

Details for the file csv_analytics_mcp-1.0.6-py3-none-any.whl.

File metadata

File hashes

Hashes for csv_analytics_mcp-1.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 9665c0f2a1a6eb020b83e0db2780095064972eb73373285ad5d54cbb8bc7bd79
MD5 4dc4909944da578b580f81f6e5fc56d1
BLAKE2b-256 c53f05498c8d2dd340cdaa2d0014dcc0c42ae32257704e3f6e6b2fe49d92023c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page